================
@@ -41,6 +41,370 @@ static SUnit *pickOnlyChoice(SchedBoundary &Zone) {
return OnlyChoice;
}
+InstructionFlavor llvm::classifyFlavor(const MachineInstr *MI,
+ const SIInstrInfo *SII) {
+ if (!MI || MI->isDebugInstr())
+ return InstructionFlavor::Other;
+
+ unsigned Opc = MI->getOpcode();
+
+ // Check for specific opcodes first.
+ if (Opc == AMDGPU::ATOMIC_FENCE || Opc == AMDGPU::S_WAIT_ASYNCCNT ||
+ Opc == AMDGPU::S_WAIT_TENSORCNT || Opc == AMDGPU::S_BARRIER_WAIT ||
+ Opc == AMDGPU::S_BARRIER_SIGNAL_IMM)
+ return InstructionFlavor::Fence;
+
+ if (Opc == AMDGPU::TENSOR_LOAD_TO_LDS_D2 ||
+ Opc == AMDGPU::TENSOR_LOAD_TO_LDS ||
+ Opc == AMDGPU::GLOBAL_LOAD_ASYNC_TO_LDS_B32 ||
+ Opc == AMDGPU::GLOBAL_LOAD_ASYNC_TO_LDS_B32_SADDR)
+ return InstructionFlavor::DMA;
+
+ if (SII->isMFMAorWMMA(*MI))
+ return InstructionFlavor::WMMA;
+
+ if (SII->isTRANS(*MI))
+ return InstructionFlavor::TRANS;
+
+ if (SII->isVALU(*MI))
+ return InstructionFlavor::SingleCycleVALU;
----------------
kerbowa wrote:
The SchedModel is mostly capturing dependent latency rather than repeat rate
which is what single cycle refers to in this example.
It's something we need to consider carefully, but downstream we've moved away
from relying on the SchedModel exclusively since it cannot effectively model
context dependent structural stalls. I think it will become more clear in
subsequent PRs.
https://github.com/llvm/llvm-project/pull/184929
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
